Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5297 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.9757. Min Act: -0.0000

Data Index: 332063 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.5392. Min Act: -0.0000

Data Index: 1225633 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.3931. Min Act: -0.0000

Data Index: 879135 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.5489. Min Act: -0.0000

Data Index: 529115 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.2846. Min Act: -0.0000

Data Index: 593655 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.2937. Min Act: -0.0000

Data Index: 813898 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.2304. Min Act: -0.0000

Data Index: 97311 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.2187. Min Act: -0.0000

Data Index: 436665 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.3050. Min Act: -0.0000

Data Index: 1143989 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.2860. Min Act: -0.0000

Data Index: 227805 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.1212. Min Act: -0.0000

Data Index: 184137 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.0919. Min Act: -0.0000

Data Index: 1327929 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.1007. Min Act: -0.0000

Data Index: 1311095 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.0253. Min Act: -0.0000

Data Index: 691548 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 2.9757. Min Range: -2.9757

Max Act: 1.8518. Min Act: -0.0000

Data Index: 982110 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 2.9757. Min Range: -2.9757

Max Act: 1.7518. Min Act: -0.0000

Data Index: 435153 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 2.9757. Min Range: -2.9757

Max Act: 1.8546. Min Act: -0.0000

Data Index: 372452 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 2.9757. Min Range: -2.9757

Max Act: 1.8375. Min Act: -0.0000

Data Index: 931947 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 2.9757. Min Range: -2.9757

Max Act: 1.9226. Min Act: -0.0000

Data Index: 1183141 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 2.9757. Min Range: -2.9757

Max Act: 1.7218. Min Act: -0.0000

Data Index: 382204 (C4 (Web Text))

Max Activating Token Index: 66